Azdaja: Jev inside an open-source RLM layer

```bash
curl -fsSL https://azdaja.dev/install | sh
```

# Azdaja

Azdaja keeps complete source material in a local evaluator and gives language models a bounded working surface for code and semantic calls. It is a **recursive language model layer**, not a model or agent harness.

[Install](#install) · [Use](#use) · [Results](#results) · [Jev](#optional-jev) · [Live proof](https://azdaja.dev/proof.html) · [Releases](https://github.com/kubet/azdaja/releases)

- **Load once:** keep full inputs in a persistent Monty/Python evaluator, not every model prompt.
- **Compute locally:** use code for parsing, filtering, joins and exact reduction.
- **Recurse selectively:** send semantic work through `llm` / `llm_batch`, then return `FINAL`. Subcalls are model calls, not new agent environments.

## Install

macOS 11+ on Apple Silicon and Intel, or x86-64 Linux with glibc 2.35+:

```bash
curl -fsSL https://azdaja.dev/install | sh
```

Choose Jcode, Claude, Codex, Gemini or OpenCode when prompted. Installation verifies downloads and makes no model calls. The installer adds `az` as an alias when available.

From source with Rust 1.95:

```bash
cargo install --git https://github.com/kubet/azdaja.git --tag v0.1.18 --locked --features typesafe
```

Remove Azdaja-managed installations:

```bash
azdaja uninstall all
```

[Install options](docs/install.md) · [LICENSE](LICENSE) · [supported-target third-party notices](THIRD-PARTY-NOTICES.md)

## Use

```bash
azdaja solo "Summarize the unresolved issues" -f ./large.txt
azdaja solo "Find release blockers" --repo ./project
```

For explicit, persistent work:

```bash
sid=$(azdaja start)
azdaja load "$sid" ./large.txt ctx
printf '%s\n' 'FINAL(len(ctx))' | azdaja exec "$sid"
azdaja final "$sid"
azdaja kill "$sid"
```

Run `azdaja` for a provider-f